INDEX

Explanations

references to legal proceedings and specific court-related terminology

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 tramonto

-0.46

muka

-0.45

伏

-0.44

 plainte

-0.43

 Piac

-0.41

 Daher

-0.41

говор

-0.41

 speciali

-0.41

 ſever

-0.41

 Rumuni

-0.40

POSITIVE LOGITS

Tikang

0.85

TagMode

0.81

ⓧ

0.75

GraphicsUnit

0.75

iss

0.74

 ModelExpression

0.74

ształ

0.70

:+:

0.70

WriteBarrier

0.70

 AssemblyCulture

0.68

Activations Density 1.906%

references to legal proceedings and specific court-related terminology

No Comments

No Known Activations